Tobias Beckman, Gerhard Waldhart, Stefan Thiem, Oliver Wohak
Our paper presents a model-based approach to quantify individual dribbles in women's soccer based on value and risk attributes. By analyzing over 48,000dribbles in the 2023 Women's World Cup using machine learning techniques, we measure the expected probability of success and the expected threat of each dribble. The results highlight players who outperform expectations, but can also be used to analyze the playing philosophy of different teams. The findings have implications for player recruitment and development as well as team tactics in women's football. The source code can be found on https://github.com/stefanthiem/xT_Dribbles_Pressure.